enestanerr/Amber
Compile repeated Claude Code workflows into tested Python programs: record the agent a few times, run the same job for 6-13x fewer tokens, with guards, drift detection and agent fallback.
field: AI / ML
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~20.2k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add github -- uv run python server_github.py $ claude mcp add slack -- uv run python ../_shared/server_slack.py $ claude mcp add playwright -- npx -y @playwright/mcp@latest --headless $ claude mcp add alerts -- uv run python ../_shared/server_slack.py $ claude mcp add shop -- uv run python server_shop.py
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add github -- uv run python server_github.py $ claude mcp add slack -- uv run python ../_shared/server_slack.py $ claude mcp add playwright -- npx -y @playwright/mcp@latest --headless $ claude mcp add alerts -- uv run python ../_shared/server_slack.py $ claude mcp add shop -- uv run python server_shop.py
$ npx degit enestanerr/Amber/plugins/amber/skills/compile .claude/skills/compile $ npx degit enestanerr/Amber/plugins/amber/skills/heal .claude/skills/heal
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (5)
| server | source | est. tokens |
|---|---|---|
| python · "github" | pypi | 2.5k |
| python · "slack" | pypi | 2.5k |
| Playwright MCP · "playwright" | npm | 7.5k |
| python · "alerts" | pypi | 2.5k |
| python · "shop" | pypi | 2.5k |
Skills (2)
Similar rigs
777genius/agent-teams-ai
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub/Kiro/Z.AI/Xiaomi
Pragmatist 12.5k tok · · Q3
kaorii-ako/Shiori-v1
Open-source AI study companion — Google Classroom sync, Gemini AI plans, SRS flashcards, GPA predictor, AI quiz, MCP server for Claude Code. Try demo at shiori-v1.vercel.app
Pragmatist 8.8k tok · · Q15
atxtechbro/dotfiles
AI-orchestration dotfiles for developers who want leverage. Parallelize agents, enforce principles, and self-heal your stack for 100x throughput. Built to version the AI era.
YOLO Cowboy 7.5k tok · · Q0
khinshankhan/dotfiles
My dotfiles. They may help you, but they mostly help me 🤔
YOLO Cowboy 7.5k tok · · Q0